• KIPS Transactions on Software and Data Engineering
• /
• v.7 no.12
• /
• pp.485-496
• /
• 2018

So far, the deep learning, a field of artificial intelligence, has achieved remarkable results in solving problems from unstructured data. However, it is difficult to comprehensively judge situations like humans, and did not reach the level of intelligence that deduced their relations and predicted the next situation. Recently, deep neural networks show that artificial intelligence can possess powerful relational reasoning that is core intellectual ability of human being. In this paper, to analyze and observe the performance of Relation Networks (RN) among the neural networks for relational reasoning, two types of RN-based deep neural network models were constructed and compared with the baseline model. One is a visual question answering RN model using Sort-of-CLEVR and the other is a text-based question answering RN model using bAbI task. In order to maximize the performance of the RN-based model, various performance improvement experiments such as hyper parameters tuning have been proposed and performed. The effectiveness of the proposed performance improvement methods has been verified by applying to the visual QA RN model and the text-based QA RN model, and the new domain model using the dialogue-based LL dataset. As a result of the various experiments, it is found that the initial learning rate is a key factor in determining the performance of the model in both types of RN models. We have observed that the optimal initial learning rate setting found by the proposed random search method can improve the performance of the model up to 99.8%.

• Korean Journal of Poultry Science
• /
• v.45 no.4
• /
• pp.285-290
• /
• 2018

This study was aimed to evaluate the possibility of application to the KS A ISO 2859-1 Easy test, an international standards sampling inspection, to replace a sampling method of the current grading standard of chicken meats for the first time. As a result of screening capability to check for defective products, the current sampling was 0.61 and the KS A ISO 2859-1 Normal test was 0.70, suggesting that the latter inspection method was more accurate. If the KS A ISO 2859-1 conversion principle is applied, 40,530 won per day is saved for a 50-lot inspection. The current sampling and the KS A ISO 2859-1 Easy test did not exceed the reject limit for the number of defective products to satisfy the grade $1^+$ on chicken carcass size numbers 12, 9 and 8. Freshness was not significantly different between the current sampling and the KS A ISO 2859-1 Easy test. It is expected that using the KS A ISO 2859-1 Easy test with a smaller sample volume will have the same level of quality evaluation as the current sampling method while reducing costs.

• Research in Plant Disease
• /
• v.24 no.4
• /
• pp.353-358
• /
• 2018

An effective bioformulation of mixtures of chitin-degrading bacteria has been used successfully to control plant diseases and nematodes. In this study, the bioformulation approach was assessed to control damping-off disease of ginseng. In pot experiments with soils infested with dapming-off pathogens of ginseng, root-drenchings of Chrobacterium sp. C-61, Lysobacterium enzymogenes C-3, and mixture of two bacterial strains grown in chitin minimal medium were signficantly increased emergence of seeds and reduced damping-off disease incidence of seedlings. Efficacy of the bioformulated product depended on the dose and timing of application. In two-year-old ginseng field, the high control efficacies were achieved by soil drenching of two times with an undiluted product or three times with a 10-fold diluted product. In a To-jik nursery (self soil nursery), biocontrol efficacy of the undiluted product against damping-off disease were similar to that of a seed dressing with fungicide, Tolclofos-methyl WP. These results suggest that the bioformulated product containing Chromobacterium sp. C-61 and L. enzymogenes C-3 could be an effective approach to control of ginseng damping-off disease.

• Economic and Environmental Geology
• /
• v.52 no.2
• /
• pp.199-212
• /
• 2019

In the machine learning techniques, the sampling strategy of the training data affects a performance of the prediction model such as generalizing ability as well as prediction accuracy. Especially, in landslide susceptibility analysis, the data sampling procedure is the essential step for setting the training data because the number of non-landslide points is much bigger than the number of landslide points. However, the previous researches did not consider the various sampling methods for the training data. That is, the previous studies selected the training data randomly. Therefore, in this study the authors proposed several different sampling methods and assessed the effect of the sampling strategies of the training data in landslide susceptibility analysis. For that, total six different scenarios were set up based on the sampling strategies of landslide points and non-landslide points. Then Random Forest technique was trained on the basis of six different scenarios and the attribute importance for each input variable was evaluated. Subsequently, the landslide susceptibility maps were produced using the input variables and their attribute importances. In the analysis results, the AUC values of the landslide susceptibility maps, obtained from six different sampling strategies, showed high prediction rates, ranges from 70 % to 80 %. It means that the Random Forest technique shows appropriate predictive performance and the attribute importance for the input variables obtained from Random Forest can be used as the weight of landslide conditioning factors in the susceptibility analysis. In addition, the analysis results obtained using specific sampling strategies for training data show higher prediction accuracy than the analysis results using the previous random sampling method.

• Journal of The Korean Association For Science Education
• /
• v.38 no.6
• /
• pp.825-838
• /
• 2018

The purpose of this study is to develop a survey tool of scientific character for elementary student which connects science education and character education effectively by figuring out traits of elementary students' character being presented in teaching and learning context of elementary school science. For this, we adapted the theocratical model from the previous research which defined scientific character as the competencies being able to practice in concrete teaching and learning context of science. Based on this model, we developed the survey tool as 'Scientific Character Inventory for Elementary Student' to assess elementary students' scientific character as the competences to practice the virtues being pursued in the context of elementary school science and verified its reliability and validity. As a result of an exploratory and confirmatory factor analysis, we confirmed all the items could be summarized into 28 items and eight constructs such as scientific problem-solving, self-management, self-reflection, communication, interpersonal skill, community participation, global citizenship, and environmental ethics awareness. We found that minimum reliability coefficient of constructs was over than 0.5 and reliability coefficient of the total items was 0.878. And also, there was modest relationship between each construct and the total score of scientific character. These results show that the developed survey tool can be useful in evaluating the effectiveness of science character education. This study is meaningful in that it systematically reveals constructs of scientific character which can be raised in concrete context of science teaching and learning so as to suggest the survey tool to assess this.

• Journal of the Korean Applied Science and Technology
• /
• v.36 no.2
• /
• pp.507-523
• /
• 2019

This purpose of study was to Analysis on Location and Service Factors Affecting the Management and Use of Judo Gym. This study aims at providing fundamental data and information on Judo coach by studying what effects of location and use factor on trainee satisfaction. The survey was done through 350 copies and excluding 11 copies ran an analysis on the remaining 339(96.8%) copies. After question investigating the data which is collected used IBM SPSS statistics 21 program, frequency analysis, Exploratory factor analysis, Cronbach's ${\alpha}$, correlation analysis, multiple regression. The result of this study were as follows. First, management, location, coach, trainee value, facility, communication in Judo gym location and use factors showed (+) effects on trainee satisfaction. Second, Program operation, Gym quit use, Whether or not to insure in management factor showed (+) effects on trainee satisfaction. Third, Coach credibility in coach factor showed (+) effects on trainee satisfaction. Forth, Member communication in communication factor showed (+) effects on trainee satisfaction. Fifth, Wholesome leisure, Athletic ability improving in trainee value factor showed (+) effects on trainee satisfaction. Sixth, main facility level, additional facility level in facility factor showed (+) effects on trainee satisfaction. Seventh, Visibility in location factor showed (+) effects on trainee satisfaction. And location type(station area, residential district, commercial area) of Judo gym showed (+) effect on management, trainee value, location, communication, facility.

• Korean Journal of Heritage: History & Science
• /
• v.46 no.2
• /
• pp.166-185
• /
• 2013

After analyzing the location, arrangement, inner structure, and form of the hunting pit in the Bronze Age, this paper sets up three types and talks about types of hunting pits. After analyzing the types of the hunting pit, three types of hunting pits are derived: mountain district - large group's arrangement - long oval - I II type(A), mountain district - arrangement in a line - oval - I type(B), flat area - arrangement in a line - oval - I III type(C). Literature, the ways in hunting pits, the purpose of the installations, and the characters are studied and compared with those of the anthropological cases. Even though hunting pits of types A and B are constructed to hide and get protein and bone of animals for breeding, there are differences in the ways in hunting and characters. Type of A seems to be constructed only for occupation that is the standardized hunting method on a small works. However, type B is the chasing method to hunt as a group and it has various purposes including main occupation. For example, it is for improving the war skills by practicing the hunting strategies and cooperating with the people. In addition, it is for getting a sacrifice for god. The type C hunting pit is estimated that it plays a role to protect themselves from invasion. It's inferred that there are many purposes for military defense and protection of people or animals within the village. It is the reason why the construction is spread in hunting pit including various purposes in the Bronze age that originates in social and economical specialization like the increase in agricultural productivity and appearance of a chief.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.25 no.1
• /
• pp.74-80
• /
• 2019

In this study, pyrolyzed oyster shells at a low temperature ($350^{\circ}C$) were applied for a mesocosm experiment to confirm resulting changes in the properties of sediment. After creating a covering of oyster shells, an increase in ORP and decrease in ammonia in the overlying water was observed in an experimental case. The decrease of TOC in this experiment was due to the dilution of organic matter due to the addition of inorganic matter (pyrolyzed oyster shells). The decrease in the concentration of AVS was observed due to the adsorption of AVS by the surface of the oyster shells. From the results obtained in this experiment, it has been concluded that pyrolyzed oyster shells at a low temperature can be used for remediation of polluted sediment.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.21 no.3
• /
• pp.196-207
• /
• 2019

This study was carried out to investigate the effects of C. japonica, D. morbifera, D. macropodum, I. anisatum, Q. glauca and R. indica To investigate the photosynthetic ability, chlorophyll content, chlorophyll fluorescence analysis, and physiological environmental. The photosynthetic rate, cancer respiration rate, stomatal conductance, and rate of evaporation tended to decrease as a result of drying stress in the no-water condition for 28 days. I. anisatum, Q. glauca and R. indica showed a low rate of less than 40% until 28 days of no-treatment. The total chlorophyll contents were decreased in the order of D. macropodum> D. morbifera> C. japonica> Q. glauca> M. thunbergii> R. indica> I. anisatum. Chlorophyll fluorescence analysis showed that there was no change in the qP, but after 28 days no $Fv/F_m$, $F_o$, $R_{fd}$, $NPQ_{_-LSS}$ can be a useful indicator for quantitative estimation within a short period of time with a marked reduction rate of PSII quantum yield ${\Phi}PSII$ in the rectified state by continuous light during the nominal adaptation period. In the case of I. anisatum, Q. glauca and R. indica If water management can be carried out at intervals, it may be possible to plant trees in trees and landscape trees.

• Journal of Life Science
• /
• v.29 no.10
• /
• pp.1086-1095
• /
• 2019

This research was performed to develop a new material consisting of a mixture of Red Allium cepa (RA) Cucurbita moschata duch (CM), and Angelica gigas Nakai (AG). RA and CM have low storage stability because of their high moisture content. Therefore, their major components were extracted and used for the research after a content analysis. In order to overcome these limitations, the quercetin from RA, ${\beta}-carotene$ from CM, and decursin/decursinol angelate (D/DA) from AG were separately extracted, and the biochemical activity of each extract and mixture was compared. RA was bioconverted by the Bacillus subtillis KJ-3 (BS3) after ethanol extraction. After bioconversion, the quercetin content of RA was increased by 128.9%. ${\beta}-carotene$ was detected in the CM ethanol extract and its content was very low concentrations at 0.2 mg/g. The AG ethanol extract (1 mg) contained 0.4146 mg and 0.3659 mg of D/DA, respectively. The purity of the D/DA was found to be about 78%. The flavonoid and polyphenol content of each extract and their mixtures (mixture 1 (RA:CM:AG = 5:2:3), mixture 2 (RA:CM: AG = 3:5:2), and mixture 3 (RA:CM:AG = 3:2:5)) were measured. In addition, the cell survival rate, anti-inflammatory activity, and antioxidant ability were also evaluated. In all the results, the antioxidant activity of mixture 3 was most effective. Therefore, these findings provide basic data for future food development using a 3:2:5 mixture of RA, CM, and AG.